---
license: mit
language:
- en
- fr
base_model:
- microsoft/Phi-3-mini-4k-instruct
pipeline_tag: text-generation
tags:
- nlp
- code
- onnx
- amd
---

# microsoft/Phi-3-mini-4k-instruct
- ## Introduction
  This model was created by applying [Quark](https://quark.docs.amd.com/latest/index.html) with calibration samples from Pile dataset, and applying [onnxruntime-genai model builder](https://github.com/microsoft/onnxruntime-genai/tree/main/src/python/py/models) to convert to ONNX.
- ## Quantization Strategy
  - AWQ / Group 128 / Asymmetric / FP32 activations
- ## Quick Start
For quickstart, refer to AMD [RyzenAI-SW-EA](https://account.amd.com/en/member/ryzenai-sw-ea.html)

#### Evaluation scores
The perplexity measurement is run on the wikitext-2-raw-v1 (raw data) dataset provided by Hugging Face. Perplexity score measured for prompt length 2k is 6.988726.

#### License

Modifications copyright(c) 2024 Advanced Micro Devices,Inc. All rights reserved.

license: [MIT license](https://huggingface.co/microsoft/Phi-3-mini-4k/resolve/main/LICENSE)